Differentially-Private Learning of Low Dimensional Manifolds

Abstract

In this paper, we study the problem of differentially-private learning of low dimensional manifolds embedded in high dimensional spaces. The problems one faces in learning in high dimensional spaces are compounded in differentially-private learning. We achieve the dual goals of learning the manifold while maintaining the privacy of the dataset by… (More)
DOI: 10.1007/978-3-642-40935-6_18

Topics

  • Presentations referencing similar topics